Upload model files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 111,
+  "<s>": 110
+}

config.json

@@ -0,0 +1,108 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 109,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 110,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4223a8256417b50da8c4551aa3a0b2aa4fc309d61f8a6805a656b698c2362bc0
+size 377851056

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "108": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "111": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbb6d968e2d20d26ad679b9de3f4490537bf869430a489b7067ea9e352de55d
+size 5240

vocab.json

@@ -0,0 +1,112 @@
+{
+  "0": 63,
+  "1": 94,
+  "2": 55,
+  "3": 4,
+  "4": 34,
+  "5": 107,
+  "6": 1,
+  "7": 11,
+  "8": 43,
+  "9": 51,
+  "<pad>": 109,
+  "<unk>": 108,
+  "a": 17,
+  "b": 36,
+  "c": 49,
+  "d": 44,
+  "e": 65,
+  "f": 77,
+  "g": 58,
+  "h": 71,
+  "i": 57,
+  "j": 22,
+  "k": 96,
+  "l": 18,
+  "m": 67,
+  "n": 26,
+  "o": 105,
+  "p": 98,
+  "q": 20,
+  "r": 47,
+  "s": 39,
+  "t": 56,
+  "u": 31,
+  "v": 15,
+  "w": 35,
+  "x": 81,
+  "y": 32,
+  "z": 87,
+  "|": 46,
+  "à": 24,
+  "á": 62,
+  "â": 72,
+  "ã": 83,
+  "è": 90,
+  "é": 27,
+  "ê": 12,
+  "ì": 40,
+  "í": 3,
+  "ò": 92,
+  "ó": 82,
+  "ô": 30,
+  "õ": 10,
+  "ù": 53,
+  "ú": 73,
+  "ý": 6,
+  "ă": 104,
+  "đ": 89,
+  "ĩ": 70,
+  "ũ": 48,
+  "ơ": 95,
+  "ư": 106,
+  "̀": 61,
+  "́": 59,
+  "̣": 86,
+  "у": 29,
+  "ạ": 50,
+  "ả": 88,
+  "ấ": 99,
+  "ầ": 41,
+  "ẩ": 7,
+  "ẫ": 97,
+  "ậ": 64,
+  "ắ": 79,
+  "ằ": 33,
+  "ẳ": 68,
+  "ẵ": 93,
+  "ặ": 76,
+  "ẹ": 103,
+  "ẻ": 0,
+  "ẽ": 100,
+  "ế": 52,
+  "ề": 9,
+  "ể": 45,
+  "ễ": 38,
+  "ệ": 37,
+  "ỉ": 101,
+  "ị": 85,
+  "ọ": 74,
+  "ỏ": 14,
+  "ố": 23,
+  "ồ": 75,
+  "ổ": 84,
+  "ỗ": 25,
+  "ộ": 66,
+  "ớ": 102,
+  "ờ": 21,
+  "ở": 8,
+  "ỡ": 54,
+  "ợ": 69,
+  "ụ": 2,
+  "ủ": 28,
+  "ứ": 13,
+  "ừ": 91,
+  "ử": 60,
+  "ữ": 78,
+  "ự": 19,
+  "ỳ": 80,
+  "ỵ": 42,
+  "ỷ": 16,
+  "ỹ": 5
+}